SceneWorks/flux1-schnell-mlx

🤗 Hugging Face sourcetext-to-imageapache-2.061 GBsafetensorsHF checksums availableupdated today
No torrent yet

FLUX.1-schnell — MLX quant matrix (bf16 / Q8 / Q4)

Pre-quantized, MLX-ready repackagings of black-forest-labs/FLUX.1-schnell for the SceneWorks native Apple-Silicon worker (mlx-gen). Each tier is a complete, self-contained turnkey snapshot that loads directly with no in-app conversion peak (epic 8506). FLUX.1-schnell is a 1–4 step timestep-distilled model (CFG-free).

Tier Subdir Approx. size
Q4 q4/ ~8.7 GB
Q8 q8/ ~17 GB
bf16 bf16/ ~31 GB

All four components are packed in Q4/Q8 — the DiT transformer, the CLIP + T5 text encoders, and the VAE's mid-block attention — using plain asymmetric group-affine quantization (group size 64), byte-identical to the worker's load-time quantization. The bf16 tier is the dense source, mirrored.

License & attribution

Apache License 2.0, inherited from the upstream FLUX.1-schnell release. © Black Forest Labs; this repository only re-packages the weights (quantization + MLX layout) and adds no new training. See LICENSE. Original model card: https://huggingface.co/black-forest-labs/FLUX.1-schnell